Gene_clustering

library(factoextra)

Loading required package: ggplot2
Welcome! Want to learn more? See two factoextra-related books at https://goo.gl/ve3WBa

library(COTAN)
library(ggrepel)
library(Rtsne)
library(plotly)

Registered S3 method overwritten by 'data.table':
  method           from
  print.data.table     
Registered S3 method overwritten by 'htmlwidgets':
  method           from         
  print.htmlwidget tools:rstudio

Attaching package: ‘plotly’

The following object is masked from ‘package:ggplot2’:

    last_plot

The following object is masked from ‘package:stats’:

    filter

The following object is masked from ‘package:graphics’:

    layout

library(tidyverse)

Registered S3 methods overwritten by 'dbplyr':
  method         from
  print.tbl_lazy     
  print.tbl_sql      
── Attaching packages ─────────────────────────────────────────────────────────── tidyverse 1.3.0 ──
✓ tibble  3.1.0     ✓ dplyr   1.0.4
✓ tidyr   1.1.2     ✓ stringr 1.4.0
✓ readr   1.4.0     ✓ forcats 0.5.1
✓ purrr   0.3.4     
── Conflicts ────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
x dplyr::filter() masks plotly::filter(), stats::filter()
x dplyr::lag()    masks stats::lag()

library(htmlwidgets)
library(MASS)

Attaching package: ‘MASS’

The following object is masked from ‘package:dplyr’:

    select

The following object is masked from ‘package:plotly’:

    select

library(dendextend)

---------------------
Welcome to dendextend version 1.14.0
Type citation('dendextend') for how to cite the package.

Type browseVignettes(package = 'dendextend') for the package vignette.
The github page is: https://github.com/talgalili/dendextend/

Suggestions and bug-reports can be submitted at: https://github.com/talgalili/dendextend/issues
Or contact: <tal.galili@gmail.com>

    To suppress this message use:  suppressPackageStartupMessages(library(dendextend))
---------------------


Attaching package: ‘dendextend’

The following object is masked from ‘package:stats’:

    cutree

library(grid)
library(ggpubr)

Attaching package: ‘ggpubr’

The following object is masked from ‘package:dendextend’:

    rotate

To demostrate how to do the gene clustering usign COTAN we begin importing the COTAN object that stores all elaborated data and, in this case, regarding a mouse embrionic cortex dataset (developmental stage E17.5).

input_dir = "Data/"
layers = list("L1"=c("Reln","Lhx5"), "L2/3"=c("Satb2","Cux1"), "L4"=c("Rorb","Sox5") , "L5/6"=c("Bcl11b","Fezf2") , "Prog"=c("Vim","Hes1"))
#objE17 = readRDS(file = paste(input_dir,"E17.5_cortex.cotan.RDS", sep = ""))
objE17 = readRDS(file = paste(input_dir,"E17_cortex_cl2.cotan.RDS", sep = ""))

g.space = get.gene.coexpression.space(objE17, 
                                      n.genes.for.marker = 25,
                                      primary.markers = unlist(layers))

[1] "calculating gene coexpression space: output tanh of reduced coex matrix"
     L11      L12    L2/31    L2/32      L41      L42    L5/61    L5/62    Prog1    Prog2 
  "Reln"   "Lhx5"  "Satb2"   "Cux1"   "Rorb"   "Sox5" "Bcl11b"  "Fezf2"    "Vim"   "Hes1" 
[1] "Get p-values on a set of genes on columns genome wide on rows"
[1] "Using function S"
[1] "function to generate S "
[1] "Secondary markers:181"
[1] "function to generate S "
[1] "Columns (V set) number: 181 Rows (U set) number: 1236"

g.space = as.data.frame(as.matrix(g.space))

coex.pca.genes <- prcomp(t(g.space),
                 center = TRUE,
                 scale. = F) 

fviz_eig(coex.pca.genes, addlabels=TRUE,ncp = 10)

#fviz_eig(coex.pca.genes, choice = "eigenvalue", addlabels=TRUE)

Hierarchical clustering

par_pca = pca_1[colnames(g.space)[colnames(g.space) %in% rownames(pca_1)],]
#plot N 1
p1 <- ggparagraph(text = paste0(rownames(par_pca[par_pca$hclust == par_pca["Fezf2","hclust"],]), collapse = ", "), 
                  face = "italic", 
                  size =10, 
                  color = "#3C5488FF")

#plot N 2
p2 = ggparagraph(text = paste0(rownames(par_pca[par_pca$hclust == unique(par_pca$hclust)[!unique(par_pca$hclust) %in% unique(par_pca[unlist(layers),"hclust"])][1],]), collapse = ", "), 
                 face = "italic", 
                 size =10, 
                 color = "gray")

#plot N 3
p3 = ggparagraph(text = paste0(rownames(par_pca[par_pca$hclust == unique(par_pca$hclust)[!unique(par_pca$hclust) %in% unique(par_pca[unlist(layers),"hclust"])][2],]), collapse = ", "), 
                 face = "italic", 
                 size =10, 
                 color = "gray")
#plot N 4
p4 = ggparagraph(text = paste0(rownames(par_pca[par_pca$hclust == par_pca["Reln","hclust"],]), collapse = ", "), 
                 face = "italic", 
                 size =10, 
                 color = "#E64B35FF")

#plot N 5
p5 = ggparagraph(text = paste0(rownames(par_pca[par_pca$hclust == par_pca["Cux1","hclust"],]), collapse = ", "), 
                 face = "italic", 
                 size =10, 
                 color = par_pca["Cux1","colors"])
#plot N 6
p6 = ggparagraph(text = paste0(rownames(par_pca[par_pca$hclust == par_pca["Rorb","hclust"],]), collapse = ", "), 
                 face = "italic", 
                 size =10, 
                 color = par_pca["Rorb","colors"])
#plot N 7
p7 = ggparagraph(text = paste0(rownames(par_pca[par_pca$hclust == par_pca["Vim","hclust"],]), collapse = ", "), 
                 face = "italic", 
                 size =10, 
                 color = par_pca["Vim","colors"])

w = ggparagraph(text = " ", 
                 face = "italic", 
                 size =10, 
                 color = "white")

pp =ggarrange(p3,p5,p1,p2,p4,p6,p7,w,
          ncol = 1, nrow = 8,
          heights = c(0.1,0.15,0.23, 0.1, 0.2, 0.2, 0.1, 0.35))

    
lay <- rbind(c(1,NA),
             c(1,2.5),
             c(1,2.5),
             c(1,2.5),
             c(1,2.5),
             c(1,2.5),
             c(1,NA))

gridExtra::grid.arrange(tree, pp, layout_matrix = lay)

or just with primary markers

# some more genes as landmarks
controls =list("genes related to L5/6"=c("Foxp2","Tbr1"), "genes related to L2/3"=c("Mef2c"), "genes related to Prog"=c("Nes","Sox2") , "genes related to L1"=c() , "genes related to L4"=c()) 
dend %>%
dendextend::set("labels", ifelse(labels(dend) %in% rownames(pca_1)[rownames(pca_1) %in% c(unlist(layers),unlist(controls))], labels(dend), "")) %>%
  dendextend::set("branches_k_color", value = c("gray80","#4DBBD5FF","#91D1C2FF" ,"gray80","#F39B7FFF","#E64B35FF","#3C5488FF"), k = 7) %>%
plot(horiz=F, axes=T,ylim = c(0,100))

Now we can plot the PCA

set.seed(NULL)
cell = sample(ncol(objE17@raw),1,replace = T)
print(cell)

[1] 676

genes.to.color.red = which(objE17@raw[,cell] > 0)
length(genes.to.color.red)

[1] 1046

pca3 = pca2 + geom_point(data = subset(pca_1, names %in% names(genes.to.color.red)), color="red")

pca3

t-SNE code and plot

# run the t-SNE
cl.genes.tsne = Rtsne(g.space ,initial_dims = 100, dims = 2, perplexity=30,eta = 200, verbose=F, max_iter = 3000,theta=0.4,num_threads = 10,pca_center = T, pca_scale = FALSE, normalize = T )

d_tsne_1 = as.data.frame(cl.genes.tsne$Y)
rownames(d_tsne_1) = rownames(g.space)

d_tsne_1 = d_tsne_1[order.dendrogram(dend),]

# save the cluster numebr inside a dataframe with the t-SNE information
d_tsne_1$hclust = cut

d_tsne_1$names = rownames(d_tsne_1)

# as before to label only some genes
textdf <- d_tsne_1[rownames(d_tsne_1) %in% c(unlist(layers),unlist(controls)),]

for (m in c(1:length(controls))) {
  for (g in controls[[m]]) {
    if(g %in% rownames(textdf)){
      textdf[g,"highlight"] = names(controls[m])
    } 
  }
}


 p1 = ggplot(subset(d_tsne_1,!hclust %in% unique(cut[unlist(layers)])), aes(x=V1, y=V2)) +  geom_point(alpha = 0.3, color = "#B09C85FF", size=1)

p2 = p1 + geom_point(data = subset(d_tsne_1, hclust %in% unique(cut[unlist(layers)]) ), aes(x=V1, y=V2, colour=as.character(hclust)),size=1,alpha = 0.5) +
    scale_color_manual("Status", values = mycolours2)  +
  scale_fill_manual("Status", values = mycolours2)  +
  xlab("") + ylab("")+
  geom_label_repel(data =textdf , aes(x = V1, y = V2, label = names,fill=as.character(hclust)),
                   label.size = NA, 
                   alpha = 0.5, 
                   direction = "both",
                   na.rm=TRUE,
                   seed = 1234) +
  geom_label_repel(data =textdf , aes(x = V1, y = V2, label = names),
                   label.size = NA, 
                   segment.color = 'black',
                   segment.size = 0.5,
                   direction = "both",
                   alpha = 1, 
                   na.rm=TRUE,
                   fill = NA,
                   seed = 1234) +
  ggtitle("t-SNE") +
  theme_light(base_size=10) +
  theme(axis.text.x=element_blank(),plot.title = element_text(size=14, 
                                    face="italic", 
                                    color="#3C5488FF",
                                    hjust=0.01,
                                    lineheight=1.2,margin = margin(t = 5, b = -15)),
        axis.text.y=element_blank(),
        legend.position = "none")  # titl)
p2

Code to create an iteractive plot. This can be modified to be used with all the plots.

p = ggplot(d_tsne_1, aes(x=V1, y=V2, text= paste("gene: ",names))) +  
  geom_point(size=2, aes(colour=as.character(hclust)), alpha=0.8) +
  scale_color_manual("Status", values = mycolours2)  +
  xlab("") + ylab("") +
  ggtitle("t-SNE") +
  theme_light(base_size=10) +
  theme(axis.text.x=element_blank(),
        axis.text.y=element_blank())

ggplotly(p)

Multidimensional scaling (MDS) and plot

sessionInfo()

R version 4.0.4 (2021-02-15)
Platform: x86_64-pc-linux-gnu (64-bit)
Running under: Ubuntu 18.04.5 LTS

Matrix products: default
BLAS:   /usr/lib/x86_64-linux-gnu/openblas/libblas.so.3
LAPACK: /usr/lib/x86_64-linux-gnu/libopenblasp-r0.2.20.so

locale:
 [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C               LC_TIME=en_US.UTF-8        LC_COLLATE=en_US.UTF-8    
 [5] LC_MONETARY=en_US.UTF-8    LC_MESSAGES=en_US.UTF-8    LC_PAPER=en_US.UTF-8       LC_NAME=C                 
 [9] LC_ADDRESS=C               LC_TELEPHONE=C             LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C       

attached base packages:
[1] grid      stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
 [1] ggpubr_0.4.0      dendextend_1.14.0 MASS_7.3-53.1     htmlwidgets_1.5.3 forcats_0.5.1     stringr_1.4.0    
 [7] dplyr_1.0.4       purrr_0.3.4       readr_1.4.0       tidyr_1.1.2       tibble_3.0.6      tidyverse_1.3.0  
[13] plotly_4.9.3      Rtsne_0.15        ggrepel_0.9.1     COTAN_0.1.0       factoextra_1.0.7  ggplot2_3.3.3    

loaded via a namespace (and not attached):
 [1] matrixStats_0.58.0   fs_1.5.0             lubridate_1.7.9.2    filelock_1.0.2       RColorBrewer_1.1-2  
 [6] httr_1.4.2           tools_4.0.4          backports_1.2.1      R6_2.5.0             DBI_1.1.1           
[11] lazyeval_0.2.2       BiocGenerics_0.36.0  colorspace_2.0-0     GetoptLong_1.0.5     withr_2.4.1         
[16] tidyselect_1.1.0     gridExtra_2.3        curl_4.3             compiler_4.0.4       cli_2.3.0           
[21] rvest_0.3.6          Cairo_1.5-12.2       basilisk.utils_1.2.2 xml2_1.3.2           labeling_0.4.2      
[26] scales_1.1.1         rappdirs_0.3.3       digest_0.6.27        foreign_0.8-81       rmarkdown_2.7       
[31] rio_0.5.16           basilisk_1.2.1       pkgconfig_2.0.3      htmltools_0.5.1.1    dbplyr_2.1.0        
[36] rlang_0.4.10         GlobalOptions_0.1.2  readxl_1.3.1         rstudioapi_0.13      gridGraphics_0.5-1  
[41] farver_2.0.3         shape_1.4.5          generics_0.1.0       jsonlite_1.7.2       crosstalk_1.1.1     
[46] zip_2.1.1            car_3.0-10           magrittr_2.0.1       Matrix_1.3-2         Rcpp_1.0.6          
[51] munsell_0.5.0        S4Vectors_0.28.1     abind_1.4-5          reticulate_1.18      viridis_0.5.1       
[56] lifecycle_0.2.0      stringi_1.5.3        yaml_2.2.1           carData_3.0-4        parallel_4.0.4      
[61] crayon_1.4.0         lattice_0.20-41      haven_2.3.1          cowplot_1.1.1        circlize_0.4.12     
[66] hms_1.0.0            knitr_1.31           ComplexHeatmap_2.6.2 pillar_1.4.7         rjson_0.2.20        
[71] ggsignif_0.6.1       stats4_4.0.4         reprex_1.0.0         glue_1.4.2           evaluate_0.14       
[76] data.table_1.13.6    modelr_0.1.8         png_0.1-7            vctrs_0.3.6          cellranger_1.1.0    
[81] gtable_0.3.0         clue_0.3-58          assertthat_0.2.1     openxlsx_4.2.3       xfun_0.20           
[86] broom_0.7.5          rstatix_0.7.0        viridisLite_0.3.0    IRanges_2.24.1       cluster_2.1.1       
[91] ellipsis_0.3.1